© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118950
    Prev
    Next
    INDEX
    Explanations

    turned into ashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IMPORTANT
    -0.82
     mascarpone
    -0.78
     établir
    -0.78
    ‹
    -0.76
    Споља
    -0.75
    جیت
    -0.75
     thyme
    -0.74
    Arrays
    -0.74
     („
    -0.74
     aplicação
    -0.73
    POSITIVE LOGITS
     ashes
    1.45
     unrecogn
    1.33
     dust
    1.15
     nothing
    1.13
     ash
    1.10
     pulp
    1.09
     powder
    1.08
     rubble
    1.07
     mulch
    1.05
     mush
    0.93
    Activations Density 0.087%

    No Known Activations